© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 215567
    Prev
    Next
    INDEX
    Explanations

    Odd jobs

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mitch
    0.48
    தும்
    0.42
     Ві
    0.41
    ቾ
    0.41
    өт
    0.39
    តុ
    0.39
    CHP
    0.39
     Coul
    0.39
     Chav
    0.39
     SHR
    0.39
    POSITIVE LOGITS
     kl
    1.48
     Kl
    1.23
    Kl
    1.22
    kl
    1.19
    คล
    1.08
     KL
    0.97
     클
    0.93
    klus
    0.93
    KL
    0.92
     क्ल
    0.89
    Activations Density 0.000%

    No Known Activations